Temporal updating scheme for probabilistic neural network with application to satellite cloud classification

In cloud classification from satellite imagery, temporal change in the images is one of the main factors that causes degradation in the classifier performance. In this paper, a novel temporal updating approach is developed for probabilistic neural network (PNN) classifiers that can be used to track temporal changes in a sequence of images. This is done by utilizing the temporal contextual information and adjusting the PNN to adapt to such changes. Whenever a new set of images arrives, an initial classification is first performed using the PNN updated up to the last frame while at the same time, a prediction using Markov chain models is also made based on the classification results of the previous frame. The results of both the old PNN and the predictor are then compared. Depending on the outcome, either a supervised or an unsupervised updating scheme is used to update the PNN classifier. Maximum likelihood (ML) criterion is adopted in both the training and updating schemes. The proposed scheme is examined on both a simulated data set and the Geostationary Operational Environmental Satellite (GOES) 8 satellite cloud imagery data. These results indicate the improvements in the classification accuracy when the proposed scheme is used.

[1]  Melba M. Crawford,et al.  Cloud-type discrimination via multispectral textural analysis , 1994 .

[2]  Roy L. Streit,et al.  Maximum likelihood training of probabilistic neural networks , 1994, IEEE Trans. Neural Networks.

[3]  D. F. Specht,et al.  Experience with adaptive probabilistic neural networks and adaptive general regression neural networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[4]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[5]  C.F.N. Cowan,et al.  Textural and spectral features as an aid to cloud classification , 1991 .

[6]  Jason I. Gobat,et al.  Improved cloud detection in GOES scenes over the oceans , 1995 .

[7]  Joann Parikh,et al.  A comparative study of cloud classification techniques , 1977 .

[8]  Marijke F. Augusteijn,et al.  Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural network classifier , 1995, IEEE Trans. Geosci. Remote. Sens..

[9]  Mahmood R. Azimi-Sadjadi,et al.  A study of cloud classification with neural networks using spectral and textural features , 1999, IEEE Trans. Neural Networks.

[10]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[11]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[12]  Ronald M. Welch,et al.  A neural network approach to cloud classification , 1990 .

[13]  Richard L. Bankert,et al.  Cloud Classification of AVHRR Imagery in Maritime Regions Using a Probabilistic Neural Network , 1994 .

[14]  David Landgrebe,et al.  Utilizing Multitemporal Data by a Stochastic Model , 1986, IEEE Transactions on Geoscience and Remote Sensing.

[15]  M.R. Azimi-Sadjadi,et al.  Neural network-based cloud detection/classification using textural and spectral features , 1996, IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium.

[16]  W. Shenk,et al.  A Multispectral Cloud Type Identification Method Developed for Tropical Ocean Areas with Nimbus-3 MRIR Measurements , 1976 .

[17]  P. H. Swain,et al.  Bayesian classification in a time-varying environment , 1978 .

[18]  D.A. Landgrebe,et al.  Classification with spatio-temporal interpixel class dependency contexts , 1992, IEEE Trans. Geosci. Remote. Sens..

[19]  Sun-Yuan Kung,et al.  Face recognition/detection by probabilistic decision-based neural network , 1997, IEEE Trans. Neural Networks.

[20]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[21]  Jason I. Gobat,et al.  Improved cloud detection in GOES scenes over land , 1995 .

[22]  D. F. Specht,et al.  Generalization accuracy of probabilistic neural networks compared with backpropagation networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[23]  Pietro Burrascano,et al.  Learning vector quantization for the probabilistic neural network , 1991, IEEE Trans. Neural Networks.

[24]  Ronald M. Welch,et al.  Polar Cloud and Surface Classification Using AVHRR Imagery: An Intercomparison of Methods , 1992 .

[25]  Thomas H. Vonder Haar,et al.  A Bispectral Method for Cloud Parameter Determination , 1977 .

[26]  Richard C. Dubes,et al.  Performance evaluation for four classes of textural features , 1992, Pattern Recognit..

[27]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[28]  S. K. Sengupta,et al.  Cloud field classification based upon high spatial resolution textural features: 1. Gray level co‐occurrence matrix approach , 1988 .